Journal of the Institute of Electronics Engineers of Korea SD (대한전자공학회논문지SD)

The Institute of Electronics and Information Engineers (대한전자공학회)
권호 표지

A Real-time SoC Design of Foreground Object Segmentation

Foreground 객체 추출을 위한 실시간 SoC 설계

  • Kim Ji-Su (School of Electrical Engineering and Computer Science, Seoul National University) ;
  • Lee Tae-Ho (School of Electrical Engineering and Computer Science, Seoul National University) ;
  • Lee Hyuk-Jae (School of Electrical Engineering and Computer Science, Seoul National University)
  • 김지수 (서울대학교 전기컴퓨터공학부) ;
  • 이태호 (서울대학교 전기컴퓨터공학부) ;
  • 이혁재 (서울대학교 전기컴퓨터공학부)
  • Published : 2006.09.01
Download PDF
⟨ Previous Next ⟩

Abstract

Recently developed MPEG-4 Part 2 compression standard provides a novel capability to handle arbitrary video objects. To support this capability, an efficient object segmentation technique is required. This paper proposes a real-time algorithm for foreground object segmentation in video sequences. The proposed algorithm consists of two steps: the first step that segments a video frame into multiple sub-regions using Spatio-Temporal Watershed Transform and the second step in which a foreground object segment is extracted from the sub-regions generated in the first step. For real-time processing, the algorithm is partitioned into hardware and software parts so that computationally expensive parts are off-loaded from a processor and executed by hardware accelerators. Simulation results show that the proposed implementation can handle QCIF-size video at 15 fps and extracts an accurate foreground object.

최근 개발된 영상 압축 표준인 MPEG-4 Part 2는 임의의 영상 객체를 처리할 수 있는 최신의 기능을 포함한다. 이러한 기능을 지원하기 위해서는 효과적인 객체 추출 기술이 요구된다. 본 논문에서는 영상 내에서 실시간으로 객체를 추출해 낼 수 있는 알고리즘을 제안한다. 제안된 알고리즘은 두 단계로 구성된다. 첫 번째 단계는 한 프레임의 영상을 시공간적 watershed transform을 이용하여 여러 영역으로 분할하는 것이고, 두 번째 단계는 분할된 영역 정보를 바탕으로 객체를 추출해내는 것이다. 실시간 처리를 위해서 제안된 알고리즘은 하드웨어와 소프트웨어로 분할하여 구현하고, 계산량이 집중된 연산 부분을 하드웨어 가속기를 사용하여 처리한다. 실험 결과 제안된 시스템은 QCIF 크기의 영상을 초당 15 frame 이상의 속도로 처리하면서도, 정확한 객체 추출 결과를 보였다.

Keywords

References

  1. ISO/IEC 14496-2, Coding of audio-visual objects Part 2: Visual, 2001
  2. Y. Tsai, C. Lai, Y. Hung, and Z.Shih, 'A Bayesian approach to video object segmentation via merging 3-D watershed volumes,' IEEE Trans. Circuits Syst. Video Technol., vol. 15, pp. 175-180, Jan. 2005 https://doi.org/10.1109/TCSVT.2004.839973
  3. S. Lee, C. Ouyang, and S.Du, 'A neuro-fuzzy approach for segmentation of human objects in image sequences,' IEEE Trans. Systems, Man and Cybernetics, Part B, vol. 33, pp. 420-437, June 2003 https://doi.org/10.1109/TSMCB.2003.811765
  4. H. Xu, Younis, A.A Younis, and M.R. Kabuka, 'Automatic moving object extraction for content-based applications,' IEEE Trans. Circuits Syst. Video Technol., vol.14, pp. 796-812, June 2004 https://doi.org/10.1109/TCSVT.2004.828338
  5. D. Wang, 'Unsupervised video segmentation based on watersheds and temporal tracking,' IEEE Trans. Circuits Syst. Video Technol., vol. 8, pp. 539-546, Sept. 1998 https://doi.org/10.1109/76.718501
  6. E. Hayman and J. Eklundh, 'Statistical background subtraction for a mobile observer,' in Proc. IEEE Int. Conf. Computer Vision, Oct. 2003, pp. 67-74 https://doi.org/10.1109/ICCV.2003.1238315
  7. S. Chien, Y. Huang, B. Hsieh, S. Ma, and L. Chen, 'Fast video segmentationalgorithm with shadow cancellation, global motion compensation, and adaptive threshold techniques,' IEEE Trans. Multimedia, vol. 6, pp. 732-748, Oct. 2004 https://doi.org/10.1109/TMM.2004.834868
  8. L. Vincent and P. Soille, 'Watersheds in digital spaces: An efficient algorithm based on immersion simulations,' IEEE Trans. Pattern Anal. Machine Intell., Vol. 13, No. 6, pp. 583-598, June 1991 https://doi.org/10.1109/34.87344
  9. L. Vincent and P. Soille, 'Morphological grayscale reconstruction in image analysis: Applications and efficient algorithms,' IEEE Trans. Image Processing, Vol. 2, No. 2, pp. 176-201, Apr. 1993 https://doi.org/10.1109/83.217222
  10. P. Salembier and M. Pardas, 'Hierarchical morphological segmentation for image sequence coding,' IEEE Trans. Image Processing, Vol. 3, No. 5, Sept. 1994 https://doi.org/10.1109/83.334980
  11. F. Meyer, 'Color image segmentation,' in Proc. Int. Conf. on Image Processing and its Applications, pp. 303-306, 1992